Contributors:

William Loving (wfl9zy) James Sweat (jes9hd)

Goals:

  • Our goal here in part 3 is to explore jobs and job satisfaction on a more granular level.
  • Find out whether or not older individuals favor non-travel working styles or overtime positions.
  • Find out if job role and distance from home have an impact on general job satisfaction.
  • Find out if job satisfaction declines as the number of years since promotion rises.
  • Find out if the marital status of individuals when working has a general trend, are more people married? Divorced? Single?

Part 3: Job Satisfaction Outside of CS/DS:

  • This data more-so concerns people and how they felt about their jobs rather than data about the job itself.
library(readr)
library(dplyr)
library(ggplot2)
library(plotly)

Load Data:

data <- read_csv("../data/job-satisfaction-data/hr_data.csv.csv")
head(data)
## # A tibble: 6 × 35
##     Age Attrition BusinessTravel DailyRate Department DistanceFromHome Education
##   <dbl> <chr>     <chr>              <dbl> <chr>                 <dbl>     <dbl>
## 1    41 Yes       Travel_Rarely       1102 Sales                     1         2
## 2    49 No        Travel_Freque…       279 Research …                8         1
## 3    37 Yes       Travel_Rarely       1373 Research …                2         2
## 4    33 No        Travel_Freque…      1392 Research …                3         4
## 5    27 No        Travel_Rarely        591 Research …                2         1
## 6    32 No        Travel_Freque…      1005 Research …                2         2
## # ℹ 28 more variables: EducationField <chr>, EmployeeCount <dbl>,
## #   EmployeeNumber <dbl>, EnvironmentSatisfaction <dbl>, Gender <chr>,
## #   HourlyRate <dbl>, JobInvolvement <dbl>, JobLevel <dbl>, JobRole <chr>,
## #   JobSatisfaction <dbl>, MaritalStatus <chr>, MonthlyIncome <dbl>,
## #   MonthlyRate <dbl>, NumCompaniesWorked <dbl>, Over18 <chr>, OverTime <chr>,
## #   PercentSalaryHike <dbl>, PerformanceRating <dbl>,
## #   RelationshipSatisfaction <dbl>, StandardHours <dbl>, …

Make Some Transformations for Ease of Understanding:

data$JobSatisfaction <- as.factor(data$JobSatisfaction)

Create Visuals:

Plot 1:

  • Despite the plot seeming starved of information, we can actually gleam some things. It seems that travel-type, age, and over-time are well distributed. There are no real patterns indicating that older people might travel less or anything like that.

Plot 2:

  • Here we once again see a lack of correlation, that job satisfaction and the distance from home / job role actually tend to be unrelated to one another. We would expect potentially high distances from home to result in lower job satisfaction, but that trend is not present in the data.

Plot 3:

  • Here we can discern that as the years since promotion go on, the job satisfaction definitely wavers, especially if the monthly rate is low and the years since promotion is high.

Plot 4:

  • Here we are simply showing that most working class people tend to be married regardless of their gender, we have significantly more monthly rate data-points for married individuals than Divorced or Single.